Text Summarization on SAMSum
Metric: ROUGE-L (higher is better)
Metric: ROUGE-L (higher is better)
| # | Model↕ | ROUGE-L▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | OmniVec2 | 63.7 | Yes | - | - | - |
| 2 | MoCa | 50.88 | No | Momentum Calibration for Text Generation | 2022-12-08 | - |
| 3 | SICK | 49.5 | No | Mind the Gap! Injecting Commonsense Knowledge fo... | 2022-09-02 | Code |
| 4 | HAT-CNNDM RL | 48.84 | No | Hierarchical Learning for Generation with Long S... | 2021-04-15 | - |
| 5 | InstructDS | 46.7 | No | Instructive Dialogue Summarization with Query Ag... | 2023-10-17 | Code |
| 6 | PEGASUS 2B + SliC | 45.89 | No | Calibrating Sequence likelihood Improves Conditi... | 2022-09-30 | - |
| 7 | ConDigSum | 45.2 | No | Topic-Aware Contrastive Learning for Abstractive... | 2021-09-10 | Code |
| 8 | BART-Large | 42.1 | No | Topic-Aware Contrastive Learning for Abstractive... | 2021-09-10 | Code |
| 9 | CriSPO 3-shot | 38.2 | No | CriSPO: Multi-Aspect Critique-Suggestion-guided ... | 2024-10-03 | Code |
| 10 | Mistral 7B + SigExt | 33.9 | No | Salient Information Prompting to Steer Content i... | 2024-10-03 | Code |
| 11 | GPT-4o (HPT) | 30 | No | Hierarchical Prompting Taxonomy: A Universal Eva... | 2024-06-18 | Code |